arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.05565cs.LG
收藏

MSDC:基于双CNN模型在非侵入式负载监测中利用多状态功耗

MSDC: Exploiting Multi-State Power Consumption in Non-intrusive Load Monitoring based on A Dual-CNN Model

College of Computer Science, Chongqing University(重庆大学计算机科学学院);School of Computer Science, The University of Auckland(奥克兰大学计算机科学学院);School of Cyberspace Science and Technology, Beijing Institute of Technology(北京理工大学网络空间安全学院);Southeast Institute of Information Technology, Beijing Institute of Technology(北京理工大学东南信息技术研究院);Strong AI Lab, The University of Auckland(奥克兰大学强人工智能实验室);Defence Industry Secrecy Examination and Certification Center(国防工业保密审查认证中心);School of Computer Science and Engineering, University of Electronic Science and Technology of China(电子科技大学计算机科学与工程学院)

Jialing He, Jiamou Liu, Zijian Zhang, Yang Chen, Yiwei Liu, Bakh Khoussainov, Liehuang Zhu

摘要:

非侵入式负载监测(NILM)旨在将聚合的电使用信号分解成电器特定的功率消耗,并且其相当于盲声源分离任务的经典示例。利用深度学习技术的最新进展,我们设计了一种新的神经NILM模型Multi-State Dual CNN(MSDC)。与以前的模型不同,MSDC明确地提取有关设备的多个状态和状态转换的信息,这反过来又调节了对设备的信号的预测。更具体地说,我们采用了双CNN架构:一个CNN用于输出状态分布,另一个用于预测每个状态的功率。一种新的技术发明,利用条件随机场(CRF)捕捉状态转换。在REDD和UK-DALE两个真实数据集上的实验表明,我们的模型在具有良好泛化能力的同时,显著优于最先进的模型,对看不见的设备实现了6%-10%的MAE增益和33%-51%的SAE增益。

英文摘要:

Non-intrusive load monitoring (NILM) aims to decompose aggregated electrical usage signal into appliance-specific power consumption and it amounts to a classical example of blind source separation tasks. Leveraging recent progress on deep learning techniques, we design a new neural NILM model Multi-State Dual CNN (MSDC). Different from previous models, MSDC explicitly extracts information about the appliance's multiple states and state transitions, which in turn regulates the prediction of signals for appliances. More specifically, we employ a dual-CNN architecture: one CNN for outputting state distributions and the other for predicting the power of each state. A new technique is invented that utilizes conditional random fields (CRF) to capture state transitions. Experiments on two real-world datasets REDD and UK-DALE demonstrate that our model significantly outperform state-of-the-art models while having good generalization capacity, achieving 6%-10% MAE gain and 33%-51% SAE gain to unseen appliances.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑